AI framework for autonomous systems in production and Industry 4.0

What are autonomous systems?

KI Framework
© Shutter2U -

The key feature of autonomous systems is that they use sensors to map their environment and can interact with it independently using actuators. For example, this paves the way for self-driving cars, robots that perform tasks autonomously, and systems that regulate themselves adaptively. Autonomous systems are made up of sensors for mapping the environment and components for the aggregation, analysis, and interpretation of data, as well as situation assessment, action planning, and actuators. A method known as deep reinforcement learning (DRL) is used to implement decision-making in autonomous systems or agents.

Aims of the application at the ADA Lovelace Center: framework for DRL algorithms

As part of the application »AI framework for autonomous systems«, there are plans to develop core expertise around deep reinforcement learning in the areas of planning, control, and strategy deduction. Another aim is to develop a framework for DRL algorithms with the capacity to simulate environments and for imitation and transfer learning.

Examples of applications include planning trajectories for nonholonomic robots subject to kinematic and dynamic constraints for deployment in Industry 4.0 environments, as well as controlling autonomous drones in industrial use cases and hydraulic pumps in press plants.